Systems and methods for prioritizing fraud cases using artificial intelligence

US20250029121A1Pending Publication Date: 2025-01-23WELLS FARGO BANK NA
View PDF 5 Cites 1 Cited by

Patent Information

Application Number
US18/906048
Authority / Receiving Office
US · United States
Patent Type
Applications(United States)
Current Assignee / Owner
Filing Date
2024-10-03
Publication Date
2025-01-23

AI Technical Summary

Technical Problem

Conventional fraud detection systems struggle to dynamically prioritize and manage fraud cases in real-time, leading to inefficiencies in resource allocation and response times.

Method used

A provider computing system that utilizes a network interface and processing circuit to receive fraud cases, update priority scores based on machine learning models, and assign cases to fraud agents for review, while also enabling automatic actions such as closing cases or transmitting alerts.

Benefits of technology

This system optimizes fraud team efforts by dynamically prioritizing fraud cases, allowing for quicker identification and action on high-priority cases, and reducing manual review of low-risk cases, thereby enhancing response efficiency and reducing financial losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US20250029121A1-D00000_ABST
    Figure US20250029121A1-D00000_ABST
Patent Text Reader

Abstract

A provider computing system includes a network interface and a processing circuit structured to receive a plurality of fraud cases where each fraud case is associated with transaction data and an initial priority score, determine an updated priority score for each fraud case based on the transaction data and case prioritization data where the case prioritization data includes a set of rules developed using a machine learning model, assign each fraud case to one of a plurality of queues, assign at least one fraud case to a fraud agent computing terminal associated with a fraud agent responsive to determining its updated priority score is at or above a threshold by moving the at least one fraud case to a cache, receive an input from the fraud agent computing terminal regarding a disposition of the at least one fraud case, and restructure the case prioritization data based on the input.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Healthcare fraud detection with machine learning

    US20140149128A1

  • Fraud detection and analysis

    US20150026027A1

  • Systems and methods for custom ranking objectives for machine learning models applicable to fraud and credit risk assessments

    US20180182029A1

  • Event processing for detection of suspicious financial activity

    US8751375B2

  • System and methods for dynamic digital threat mitigation

    US9954879B1

Cited By

  • Systems and methods for training and applying machine learning systems in fraud detection

    US20260037979A1